github-actions[bot] commented on PR #6148: URL: https://github.com/apache/texera/pull/6148#issuecomment-4885334828
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 6 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `92b7fc9` benchmarked on **this same runner**, so the delta is largely free of cross-runner hardware noise. The "7d avg" column still reflects the gh-pages dashboard. Treat <±5% as noise unless repeated. [Dashboard](https://apache.github.io/texera/dev/bench/) · [Run](https://github.com/apache/texera/actions/runs/28734153800) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 504 | 0.307 | 18,879/29,961/29,961 us | 🔴 +13.7% / 🔴 +97.9% | | 🔴 | bs=100 sw=10 sl=64 | 1,105 | 0.674 | 89,103/116,416/116,416 us | 🔴 +12.4% / 🟢 -12.4% | | ⚪ | bs=1000 sw=10 sl=64 | 1,246 | 0.76 | 802,723/849,737/849,737 us | ⚪ within ±5% / 🟢 +22.6% | <details><summary>Baseline details</summary> Latest main `92b7fc9` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 504 tuples/sec | 531 tuples/sec | 776.36 tuples/sec | -5.1% | -35.1% | | bs=10 sw=10 sl=64 | MB/s | 0.307 MB/s | 0.324 MB/s | 0.474 MB/s | -5.2% | -35.2% | | bs=10 sw=10 sl=64 | p50 | 18,879 us | 18,259 us | 12,636 us | +3.4% | +49.4% | | bs=10 sw=10 sl=64 | p95 | 29,961 us | 26,348 us | 15,143 us | +13.7% | +97.9% | | bs=10 sw=10 sl=64 | p99 | 29,961 us | 26,348 us | 18,954 us | +13.7% | +58.1% | | bs=100 sw=10 sl=64 | throughput | 1,105 tuples/sec | 1,123 tuples/sec | 985.33 tuples/sec | -1.6% | +12.1% | | bs=100 sw=10 sl=64 | MB/s | 0.674 MB/s | 0.686 MB/s | 0.601 MB/s | -1.7% | +12.1% | | bs=100 sw=10 sl=64 | p50 | 89,103 us | 86,654 us | 101,671 us | +2.8% | -12.4% | | bs=100 sw=10 sl=64 | p95 | 116,416 us | 103,529 us | 107,939 us | +12.4% | +7.9% | | bs=100 sw=10 sl=64 | p99 | 116,416 us | 103,529 us | 113,798 us | +12.4% | +2.3% | | bs=1000 sw=10 sl=64 | throughput | 1,246 tuples/sec | 1,241 tuples/sec | 1,016 tuples/sec | +0.4% | +22.6% | | bs=1000 sw=10 sl=64 | MB/s | 0.76 MB/s | 0.758 MB/s | 0.62 MB/s | +0.3% | +22.5% | | bs=1000 sw=10 sl=64 | p50 | 802,723 us | 804,240 us | 989,693 us | -0.2% | -18.9% | | bs=1000 sw=10 sl=64 | p95 | 849,737 us | 861,942 us | 1,028,327 us | -1.4% | -17.4% | | bs=1000 sw=10 sl=64 | p99 | 849,737 us | 861,942 us | 1,059,969 us | -1.4% | -19.8% | </details> <details><summary>Raw CSV</summary> ```csv config_idx,batch_size,schema_width,string_len,num_batches,total_ms,total_tuples,total_bytes,tuples_per_sec,mb_per_sec,lat_p50_us,lat_p95_us,lat_p99_us 0,10,10,64,20,397.03,200,128000,504,0.307,18879.26,29961.05,29961.05 1,100,10,64,20,1810.60,2000,1280000,1105,0.674,89103.00,116416.04,116416.04 2,1000,10,64,20,16056.30,20000,12800000,1246,0.760,802722.50,849736.79,849736.79 ``` </details> -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
